Search NASA⌕ Search

SEARCH · Search NASA

Results for “Word Embeddings”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2018

Retrofitting Word Embeddings with the UMLS Metathesaurus for Clinical Information Extraction

Deep learning has surged in popularity and proven to be effective for various artificial intelligence applications including information extraction from cancer pathology reports. Since word representation is a core unit that enables deep learning algorithms to understand words and be able to perform NLP, this representation must include as much information as possible to help these algorithms achieve high classification performance. Therefore, in this work in addition to the distributional information of words in large sized corpora, we use UMLS vocabulary resources to enrich the vector space representation of words with the semantic relations between words. These resources provide many terminologies pertaining to cancer. The refined word embeddings are used with a convolutional neural (CNN) model to extract four data elements from cancer pathology reports; ICD-O-3 tumor topography codes, tumor laterality, behavior, and histological grade. We observed that using UMLS vocabulary resources to enrich word embeddings of CNN models consistently outperformed CNN models without pre-training word embeddings and even with pre-trained word embeddings on a domain specific corpus across all four tasks. The results show marginal improvement on the laterality task, but a significant improvement on the other tasks, especially for the macro-f score. Specifically, the improvements are 3%, 13%, and 15% for tumor site, histological grade, and behavior tasks, respectively. This approach is encouraging to enrich word embeddings with more clinical data resources to be used for information abstraction tasks from clinical pathology reports.

Alawad, Mohammed↗
DOE OSTI2019

Computationally Efficient Learning of Quality Controlled Word Embeddings for Natural Language Processing

Deep learning (DL) has been used for many natural language processing (NLP) tasks due to its superior performance as compared to traditional machine learning approaches. In DL models for NLP, words are represented using word embeddings, which capture both semantic and syntactic information in text. However, 90-95% of the DL trainable parameters are associated with the word embeddings, resulting in a large storage or memory footprint. Therefore, reducing the number of word embedding parameters is critical, especially with the increase of vocabulary size. In this work, we propose a novel approximate word embeddings approach for convolutional neural networks (CNNs) used for text classification tasks. The proposed approach significantly reduces the number of model trainable parameters without noticeably sacrificing in computing performance accuracy. Compared to other techniques, our proposed word embeddings technique does not require modifications to the DL model architecture. We evaluate the performance of the the proposed word embeddings on three classification tasks using two datasets, composed of Yelp and Amazon reviews. The results show that the proposed method can reduce the number of word embeddings parameters by 98% and 99% for the Yelp and Amazon datasets respectively, with no drop in computing accuracy.

Alawad, Mohammed↗
DOE OSTI2021

An Introduction to Word Embeddings and Language Models

Language models have advanced at a phenomenal pace over the past decade. This document provides a short introduction to terminology, word embeddings (aka low-dimensional representations), and popular large-scale language models (LMs). Word embeddings are used to represent words as numerical vectors and are context-independent, meaning a word can only have a single representation (e.g., club can only be club sandwich, not golf club ). Language models can determine the probability of a given sequence of words occurring in a sentence and can provide context to distinguish between words and phrases that sound similar. LMs are context-dependent (e.g., club can be club sandwich or golf club ) and largely fall in two main classes – autoregressive and autoencoding models. Autoregressive models are pretrained on the classic language modeling task: guess the next token having read all the previous ones. Those models can be fine-tuned and achieve great results on many tasks, the most natural application is text generation. A typical example of such models is GPT, but others include GPT-2, GPT-3, CTLR, TRANSFORMER-XL, REFORMER, XLNET. Autoencoding models are pretrained by corrupting the input tokens in some way and trying to reconstruct the original sentence. They can be fine-tuned and achieve great results on many tasks such as text generation, but their most natural application is sentence classification or token classification. A typical example of such models is BERT, but others include ROBERTA, ALBERT, XML, XML-ROBERTA, FLAUBERT AND LONGFORMER.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2017

Visual Exploration of Semantic Relationships in Neural Word Embeddings

Constructing distributed representations for words through neural language models and using the resulting vector spaces for analysis has become a crucial component of natural language processing (NLP). But, despite their widespread application, little is known about the structure and properties of these spaces. To gain insights into the relationship between words, the NLP community has begun to adapt high-dimensional visualization techniques. Particularly, researchers commonly use t-distributed stochastic neighbor embeddings (t-SNE) and principal component analysis (PCA) to create two-dimensional embeddings for assessing the overall structure and exploring linear relationships (e.g., word analogies), respectively. Unfortunately, these techniques often produce mediocre or even misleading results and cannot address domain-specific visualization challenges that are crucial for understanding semantic relationships in word embeddings. We introduce new embedding techniques for visualizing semantic and syntactic analogies, and the corresponding tests to determine whether the resulting views capture salient structures. Additionally, we introduce two novel views for a comprehensive study of analogy relationships. Finally, we augment t-SNE embeddings to convey uncertainty information in order to allow a reliable interpretation. Combined, the different views address a number of domain-specific tasks difficult to solve with existing tools.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Understanding Event Trajectories Across Massive Temporal Datasets with Word Embeddings and Visualization

In collaboration with researchers from Virginia Tech, Savannah River National Laboratory has continued development of a natural language processing pipeline to identify and extract events of interest from massive open data sources in the domain of worldwide state-sponsored civil nuclear energy. The foundation of the pipeline is built on compass aligned temporal word embedding models, whereby contextual shifts are automatically identified by comparing keyword embedding vectors across successive time windows. Within the approach, a contextual shift indicates the occurrence of a potential event of interest. However, in such a broad topical domain that captures events at a global scale, across various life cycle stages, and across numerous different technology types, a user that is monitoring events may have broad interests in capturing many different event types with varying degrees of signal. As such, the quantity of information that may be returned from an automated event extraction pipeline can be substantial, requiring manual effort to sift through the information to identify any relevant bits of information. Therefore, a more streamlined workflow that aids in directing a user toward specific information at different points in time is necessary. The workflow presented here has been developed with this concept in mind, built on top of the initial prototype event extraction pipeline, whereby a user can analyze temporal text-based data sources at multiple different contextual levels to isolate key points in time and key subdomains captured within a data corpus. Using multiple corpuses that consist of approximately 7 million Tweets and 7 million news articles, the team has extended compass aligned temporal word embedding models to establish an interconnected and hierarchical structure that relates known key words of interest to documents, local topics (i.e., within a time window), and global topics across the corpuses. All of this information is packaged into a visual analytics system that is linked to the information extraction pipeline and enables a user to identify contextual information that describes the evolution of a high dimensional embedding space across time to isolate changes of interest and explore associated events. This report demonstrates the use of these analytics and a means to fuse information across multiple datasets.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

Unsupervised word embeddings capture latent knowledge from materials science literature

The overwhelming majority of scientific knowledge is published as text, which is difficult to analyse by either traditional statistical analysis or modern machine learning methods. By contrast, the main source of machine-interpretable data for the materials research community has come from structured property databases, which encompass only a small fraction of the knowledge present in the research literature. Beyond property values, publications contain valuable knowledge regarding the connections and relationships between data items as interpreted by the authors. To improve the identification and use of this knowledge, several studies have focused on the retrieval of information from scientific literature using supervised natural language processing, which requires large hand-labelled datasets for training. Here we show that materials science knowledge present in the published literature can be efficiently encoded as information-dense word embeddings (vector representations of words) without human labelling or supervision. Without any explicit insertion of chemical knowledge, these embeddings capture complex materials science concepts such as the underlying structure of the periodic table and structure-property relationships in materials. Furthermore, we demonstrate that an unsupervised method can recommend materials for functional applications several years before their discovery. This suggests that latent knowledge regarding future discoveries is to a large extent embedded in past publications. Lastly, our findings highlight the possibility of extracting knowledge and relationships from the massive body of scientific literature in a collective manner, and point towards a generalized approach to the mining of scientific literature.

36 MATERIALS SCIENCE↗
DOE OSTI2021

Machine learning with persistent homology and chemical word embeddings improves prediction accuracy and interpretability in metal-organic frameworks

Machine learning has emerged as a powerful approach in materials discovery. Its major challenge is selecting features that create interpretable representations of materials, useful across multiple prediction tasks. We introduce an end-to-end machine learning model that automatically generates descriptors that capture a complex representation of a material’s structure and chemistry. This approach builds on computational topology techniques (namely, persistent homology) and word embeddings from natural language processing. It automatically encapsulates geometric and chemical information directly from the material system. We demonstrate our approach on multiple nanoporous metal–organic framework datasets by predicting methane and carbon dioxide adsorption across different conditions. Our results show considerable improvement in both accuracy and transferability across targets compared to models constructed from the commonly-used, manually-curated features, consistently achieving an average 25–30% decrease in root-mean-squared-deviation and an average increase of 40–50% in R 2 scores. A key advantage of our approach is interpretability: Our model identifies the pores that correlate best to adsorption at different pressures, which contributes to understanding atomic-level structure–property relationships for materials design.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Explaining word embeddings with perfect fidelity: a case study in predicting research impact

The best-performing approaches for scholarly document quality prediction are based on embedding models. In addition to their performance when used in classifiers, embedding models can also provide predictions even for words that were not contained in the labelled training data for the classification model, which is important in the context of the ever-evolving research terminology. Although model-agnostic explanation methods, such as Local interpretable model-agnostic explanations, can be applied to explain machine learning classifiers trained on embedding models, these produce results with questionable correspondence to the model. We introduce a new feature importance method, Self-Model Entities Rated (SMER), for logistic regression-based classification models trained on word embeddings. We show that SMER has theoretically perfect fidelity with the explained model, as the average of logits of SMER scores for individual words (SMER explanation) exactly corresponds to the logit of the prediction of the explained model. Quantitative and qualitative evaluation is performed through five diverse experiments conducted on 50,000 research articles (papers) from the CORD-19 corpus. In conclusion, through an AOPC curve analysis, we experimentally demonstrate that SMER produces better explanations than LIME, SHAP and global tree surrogates.

Coarse-grained models↗
DOE OSTI2021

Supervised learning with word embeddings derived from PubMed captures latent knowledge about protein kinases and cancer

Abstract Inhibiting protein kinases (PKs) that cause cancers has been an important topic in cancer therapy for years. So far, almost 8% of >530 PKs have been targeted by FDA-approved medications, and around 150 protein kinase inhibitors (PKIs) have been tested in clinical trials. We present an approach based on natural language processing and machine learning to investigate the relations between PKs and cancers, predicting PKs whose inhibition would be efficacious to treat a certain cancer. Our approach represents PKs and cancers as semantically meaningful 100-dimensional vectors based on word and concept neighborhoods in PubMed abstracts. We use information about phase I-IV trials in ClinicalTrials.gov to construct a training set for random forest classification. Our results with historical data show that associations between PKs and specific cancers can be predicted years in advance with good accuracy. Our tool can be used to predict the relevance of inhibiting PKs for specific cancers and to support the design of well-focused clinical trials to discover novel PKIs for cancer therapy.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Teaching AI when to care about gender

Natural Language Processing (NLP) is a branch of Artificial Intelligence (AI) concerned with solving language tasks by modeling large amounts of textual data. Some NLP techniques use word embeddings which are semantic models where machine learning (ML) is used to learn to cluster semantically related words by learning about word co-occurrences in the original training text. Unfortunately, these models tend to reflect or even exaggerate biases that are present in the training corpus. Here we describe the Word Embedding Navigator (WEN), which is a tool for exploring word embedding models. We examine a specific potential use case for this tool: interactive discovery and neutralization of gender bias in word embedding models, and compare this human-in-the-loop approach to reducing bias in word embeddings with a debiasing post-processing technique.

97 MATHEMATICS AND COMPUTING↗
NASA NTRSDate not supplied

Trust-Informed Large Language Models via Word Embedding-Knowledge Graph Alignment

A major weakness of a Large Language Model (LLM) is its tendency to accept information at face value, often leading to injection of erroneous information and inducing a greater probability of hallucinating non-existent information. While Retrieval Augmented Generation (RAG) uses external knowledge sources to bolster LLMs through grounded truth, this work seeks to explore methods to engender a LLM with an intrinsic capability to evaluate an input’s believability without relying on external knowledge sources. We investigate unifying a LLM with a Knowledge Graph (KG) and using the KG to reinforce the LLM’s internal word embedding while also maintaining belief metrics along the edge’s in the KG.

Large Language Model↗
DOE OSTI2020

Multimodal Data Representation with Deep Learning for Extracting Cancer Characteristics from Clinical Text

This paper presents a multimodal data representation to improve the performance of deep learning models for extracting cancer key characteristics from unstructured text in pathology reports. Specifically, in addition to using the text as the input to deep learning models, we use concept unique identifiers (CUIs) as another source of information to the models. We analyze the performance of different text and CUI data representations, including word embeddings and bag of embeddings (BOE), with a convolutional neural network (CNN) and a fully connected multilayer perceptron neural network (MLP-NN). The high level document embeddings from text and CUI inputs are combined by concatenating them and then applying a classifier. The model is used for extracting cancer subsite and histology from pathology reports. These two classification tasks have a large number of labels, i.e. 317 for subsite and 556 for histology, with extreme class imbalance. We compare the performance of the developed DL models across the two tasks based on micro- and macro-F1 scores. The evaluation shows that a multi-channel DL model that utilizes text represented by word embeddings and CUIs represented by BOE outperforms other DL models. Also, this approach significantly improves the model performance on low prevalence classes.

Alawad, Mohammed↗
DOE OSTI2026

Evolving language of pediatric anxiety in electronic health records

Objectives This study aimed to identify and quantify semantic drift (ie, the change in semantic meaning over time) within expert-defined anxiety-related (AR) terminology and compare it to common electronic health record (EHR) vocabulary across longitudinal pediatric clinical notes. Materials and Methods A corpus of pediatric clinical notes from 2009 to 2022 was analyzed using computational methods. Semantic drift for each term was quantified using cosine similarity between annual temporal word embeddings. Contextual meaning was examined through changes in nearest neighbors across years. The Laws of Semantic Change were applied to assess the influence of word frequency and polysemy. Vocabulary terms were categorized as AR or common EHR. Results 98% of AR terminology maintained a cosine similarity between 0.00 and 0.50, indicating moderate semantic stability, whereas 90% of common EHR terms remained between 0.00 and 0.25, showing greater contextual stability overall. Frequent terms exhibited minimal change (Frequency Coefficient = 0.04), whereas highly polysemous or abbreviated terms showed less stability (Polysemy Coefficient = 0.630). AR terminology drifted more slowly than general EHR vocabulary (Type Coefficient = −0.179), further supported by significant year–type interactions (Coef = −0.09 to −0.523). Discussion Although anxiety-related terminology demonstrates slower semantic drift than general EHR vocabulary, subtle contextual shifts still occur that may affect downstream interpretability and retrieval in automated systems. Conclusion Continuous linguistic monitoring and adaptive modeling are essential to maintain semantic fidelity and ensure the long-term reliability of clinical decision support systems as healthcare documentation evolves.

Pediatric anxiety disorders↗
DOE OSTI2019

Creating Training Data for Scientific Named Entity Recognition with Minimal Human Effort

Scientific Named Entity Referent Extraction is often more complicated than traditional Named Entity Recognition (NER). For example, in polymer science, chemical structure may be encoded in a variety of nonstandard naming conventions, and authors may refer to polymers with conventional names, commonly used names, labels (in lieu of longer names), synonyms, and acronyms. As a result, accurate scientific NER methods are often based on task-specific rules, which are difficult to develop and maintain, and are not easily generalized to other tasks and fields. Machine learning models require substantial expert-annotated data for training. Here we propose polyNER: a semi-automated system for efficient identification of scientific entities in text. PolyNER applies word embedding models to generate entity-rich corpora for productive expert labeling, and then uses the resulting labeled data to bootstrap a context-based word vector classifier. Evaluation on materials science publications shows that the polyNER approach enables improved precision or recall relative to a state-of-the-art chemical entity extraction system at a dramatically lower cost: it required just two hours of expert time, rather than extensive and expensive rule engineering, to achieve that result. This result highlights the potential for human-computer partnership for constructing domain-specific scientific NER systems.

Crowdsourcing↗